{"id":31663938,"url":"https://github.com/pc-2208/multi-agent-game-tester-poc","last_synced_at":"2026-04-02T01:03:10.074Z","repository":{"id":316960267,"uuid":"1065469294","full_name":"PC-2208/Multi-Agent-Game-Tester-POC","owner":"PC-2208","description":"Multi-Agent Game Tester POC - Intelligent AI agent coordination for automated game testing with concurrent execution, comprehensive validation, and real-time reporting. Features specialized agents for planning, ranking, execution, and analysis of web-based game tests.","archived":false,"fork":false,"pushed_at":"2025-09-27T20:31:40.000Z","size":13484,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-27T22:09:33.628Z","etag":null,"topics":["fastapi","html","nodejs","openai","playwright","python","testing"],"latest_commit_sha":null,"homepage":"http://localhost:8000/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/PC-2208.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-27T19:45:53.000Z","updated_at":"2025-09-27T20:31:44.000Z","dependencies_parsed_at":"2025-09-27T22:19:38.522Z","dependency_job_id":null,"html_url":"https://github.com/PC-2208/Multi-Agent-Game-Tester-POC","commit_stats":null,"previous_names":["pc-2208/multi-agent-game-tester-poc"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/PC-2208/Multi-Agent-Game-Tester-POC","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PC-2208%2FMulti-Agent-Game-Tester-POC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PC-2208%2FMulti-Agent-Game-Tester-POC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PC-2208%2FMulti-Agent-Game-Tester-POC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PC-2208%2FMulti-Agent-Game-Tester-POC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PC-2208","download_url":"https://codeload.github.com/PC-2208/Multi-Agent-Game-Tester-POC/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PC-2208%2FMulti-Agent-Game-Tester-POC/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278846308,"owners_count":26056090,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-07T02:00:06.786Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["fastapi","html","nodejs","openai","playwright","python","testing"],"created_at":"2025-10-07T20:52:08.189Z","updated_at":"2025-10-07T20:52:09.177Z","avatar_url":"https://github.com/PC-2208.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Multi-Agent Game Tester POC\r\n\r\nA proof-of-concept implementation of an intelligent multi-agent system for automated game testing, featuring AI-powered test planning, execution, validation, and comprehensive reporting.\r\n\r\n##  Overview\r\n\r\nThis project demonstrates a sophisticated multi-agent architecture that automates the entire game testing lifecycle. The system uses multiple specialized AI agents working in coordination to plan, execute, validate, and analyze test cases for web-based games, specifically targeting `https://play.ezygamers.com/`.\r\n\r\n## Architecture\r\n\r\nThe system consists of four main agent types working in harmony:\r\n\r\n### 1. **Planner Agent** (`planner.py`)\r\n- Generates 20+ candidate test cases automatically\r\n- Creates structured test scenarios with steps, assertions, and metadata\r\n- Provides test case templates for different game scenarios\r\n\r\n### 2. **Ranker Agent** (`agents/ranker_agent.py`)\r\n- Intelligently ranks and prioritizes test cases\r\n- Selects the top 10 most valuable tests for execution\r\n- Uses scoring algorithms to optimize test coverage\r\n\r\n### 3. **Executor Agents** (`executor.py`, `executor_simple.py`)\r\n- Execute test cases using Playwright for browser automation\r\n- Capture comprehensive artifacts (screenshots, DOM, console logs, network traffic)\r\n- Support both real browser execution and simulated execution modes\r\n- Implement load balancing across multiple concurrent executors\r\n\r\n### 4. **Analyzer Agent** (`agents/analyzer_agent.py`)\r\n- Validates test results through multiple validation strategies\r\n- Performs repeat validation for reproducibility testing\r\n- Implements cross-agent validation for consensus building\r\n- Generates detailed validation reports with confidence scores\r\n\r\n### 5. **Orchestrator Agent** (`orchestrator.py`)\r\n- Coordinates all agents and manages the testing workflow\r\n- Implements concurrent execution with load balancing\r\n- Generates comprehensive test reports\r\n- Provides recommendations based on test results\r\n\r\n## Features\r\n\r\n- **Multi-Agent Coordination**: Specialized agents working together for comprehensive testing\r\n- **Concurrent Execution**: Parallel test execution with configurable concurrency limits\r\n- **Comprehensive Artifacts**: Screenshots, DOM snapshots, console logs, network traffic\r\n- **Intelligent Validation**: Multi-layered validation with reproducibility testing\r\n- **Real-time Reporting**: Live test execution reports with detailed analytics\r\n- **Web Interface**: User-friendly dashboard for monitoring and control\r\n- **RESTful API**: Complete API for integration with external systems\r\n- **Performance Metrics**: Detailed performance analysis and timing data\r\n\r\n## Prerequisites\r\n\r\n- Python 3.8+\r\n- Node.js (for Playwright)\r\n- Modern web browser (Chrome/Chromium)\r\n\r\n## Installation\r\n\r\n1. **Clone the repository**\r\n   ```bash\r\n   git clone \u003crepository-url\u003e\r\n   cd multi-agent-game-tester-poc\r\n   ```\r\n\r\n2. **Install Python dependencies**\r\n   ```bash\r\n   pip install -r requirements.txt\r\n   ```\r\n\r\n3. **Install Playwright browsers**\r\n   ```bash\r\n   playwright install\r\n   ```\r\n\r\n4. **Run the application**\r\n   ```bash\r\n   python main.py\r\n   ```\r\n\r\n5. **Access the web interface**\r\n   Open your browser and navigate to `http://localhost:8000`\r\n\r\n##  Usage\r\n\r\n### Web Interface\r\nThe system provides a user-friendly web interface where you can:\r\n- View test execution status in real-time\r\n- Generate and rank test cases\r\n- Execute comprehensive test suites\r\n- View detailed reports and analytics\r\n- Download test artifacts\r\n\r\n### API Endpoints\r\n\r\n#### Generate Test Plan\r\n```bash\r\nGET /plan\r\n```\r\nReturns 20+ candidate test cases generated by the Planner Agent.\r\n\r\n#### Rank Test Cases\r\n```bash\r\nGET /rank\r\n```\r\nRanks test cases and returns the top 10 most valuable tests.\r\n\r\n#### Execute Tests\r\n```bash\r\nPOST /execute\r\n```\r\nExecutes the top 10 ranked test cases with multiple agents.\r\n\r\n#### Get Test Report\r\n```bash\r\nGET /reports/{run_id}\r\n```\r\nRetrieves a detailed test execution report for a specific run.\r\n\r\n#### List All Reports\r\n```bash\r\nGET /reports\r\n```\r\nLists all available test execution reports.\r\n\r\n### Programmatic Usage\r\n\r\n```python\r\nfrom orchestrator import OrchestratorAgent\r\nfrom planner import generate_plan\r\nfrom agents.ranker_agent import RankerAgent\r\n\r\n# Generate test cases\r\ntest_cases = generate_plan(20)\r\n\r\n# Rank and select top tests\r\nranker = RankerAgent()\r\ntop_tests = ranker.rank_test_cases(test_cases, top_n=10)\r\n\r\n# Execute with orchestrator\r\norchestrator = OrchestratorAgent(max_concurrent_executors=3)\r\nrun_id = await orchestrator.run_tests_async(top_tests)\r\n```\r\n\r\n## Test Execution Flow\r\n\r\n1. **Planning Phase**: Planner Agent generates 20+ test case candidates\r\n2. **Ranking Phase**: Ranker Agent evaluates and selects top 10 tests\r\n3. **Execution Phase**: Multiple Executor Agents run tests concurrently\r\n4. **Validation Phase**: Analyzer Agent validates results with multiple strategies\r\n5. **Reporting Phase**: Orchestrator generates comprehensive reports\r\n\r\n## Project Structure\r\n\r\n```\r\nmulti-agent-game-tester-poc/\r\n├── agents/                    # Specialized agent implementations\r\n│   ├── analyzer_agent.py     # Test result validation agent\r\n│   └── ranker_agent.py       # Test case ranking agent\r\n├── frontend/                  # Web interface\r\n│   └── index.html            # Dashboard UI\r\n├── runs/                     # Test execution results\r\n│   └── {run_id}/            # Individual test run artifacts\r\n├── executor.py               # Full-featured executor agent\r\n├── executor_simple.py        # Simplified executor for testing\r\n├── main.py                   # FastAPI application entry point\r\n├── orchestrator.py           # Multi-agent coordination\r\n├── planner.py                # Test case generation\r\n├── test_flow.py             # End-to-end testing script\r\n└── requirements.txt         # Python dependencies\r\n```\r\n\r\n## Configuration\r\n\r\n### Concurrency Settings\r\n```python\r\n# Configure maximum concurrent executors\r\norchestrator = OrchestratorAgent(max_concurrent_executors=3)\r\n```\r\n\r\n### Validation Settings\r\n```python\r\n# Configure validation parameters\r\nanalyzer = AnalyzerAgent()\r\nanalyzer.validation_runs = 3  # Number of repeat validations\r\nanalyzer.cross_agent_threshold = 0.8  # Agreement threshold\r\n```\r\n\r\n## Test Reports\r\n\r\nEach test run generates comprehensive reports including:\r\n- **Summary Statistics**: Pass/fail rates, execution times, validation scores\r\n- **Individual Test Results**: Detailed results for each test case\r\n- **Artifacts**: Screenshots, DOM snapshots, console logs, network traffic\r\n- **Validation Details**: Repeat validation and cross-agent analysis\r\n- **Recommendations**: Actionable insights based on test results\r\n- **Performance Metrics**: Load times, rendering performance, network analysis\r\n\r\n## Testing\r\n\r\nRun the complete test suite:\r\n```bash\r\npython test_flow.py\r\n```\r\n\r\nThis will test all API endpoints and verify the complete multi-agent workflow.\r\n\r\n## Target Application\r\n\r\nThe system is specifically designed to test web-based games, with the current target being `https://play.ezygamers.com/`. The test cases are structured to validate:\r\n- Game loading and initialization\r\n- User interactions and gameplay mechanics\r\n- Visual elements and UI components\r\n- Performance and responsiveness\r\n- Error handling and edge cases\r\n\r\n## Future Enhancements\r\n\r\n- **Machine Learning Integration**: AI-powered test case generation and optimization\r\n- **Visual Testing**: Automated visual regression testing\r\n- **Performance Benchmarking**: Advanced performance analysis and comparison\r\n- **Test Data Management**: Dynamic test data generation and management\r\n- **Integration Testing**: API and database integration testing\r\n- **Mobile Testing**: Support for mobile game testing\r\n- **Cloud Execution**: Distributed testing across multiple environments\r\n\r\n\r\n\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpc-2208%2Fmulti-agent-game-tester-poc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpc-2208%2Fmulti-agent-game-tester-poc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpc-2208%2Fmulti-agent-game-tester-poc/lists"}